构建首个覆盖真实用药场景的药片实例分割数据集，助力智能防错用药。
A dataset of medication images with instance segmentation masks for preventing adverse drug events
- 采集8262张真实场景药片图像，标注32类药片实例
- YOLO模型在3药片和32药片场景下分别达99.5%与80.1%精度
- 支持少样本学习，提升遮挡多药片情况下的识别能力
药物错误和不良药物事件严重威胁患者安全，常因真实场景中药品难以准确识别所致。现有药片图像数据集缺乏对重叠、光照变化和遮挡等复杂情况的覆盖。MEDISEG 数据集提供32种药片类型在8262张图像中的实例分割标注，涵盖单片到杂乱药盒等多种场景。我们使用 YOLOv8 和 YOLOv9 在 MEDISEG 上训练，3药片子集上达到 99.5% 的 IoU=0.5 时平均精度，32药片子集为 80.1%。在少样本检测协议下评估显示，基于 MEDISEG 的预训练显著提升对未见药片类别的识别能力，尤其在遮挡多药片场景中。结果表明该数据集不仅能支持强监督训练，还可促进有限监督下的可迁移表征，是开发和评测智能用药安全系统的宝贵资源。
原文摘要 · Abstract (English)
Medication errors and adverse drug events (ADEs) pose significant risks to patient safety, often arising from difficulties in reliably identifying pharmaceuticals in real-world settings. AI-based pill recognition models offer a promising solution, but the lack of comprehensive datasets hinders their development. Existing pill image datasets rarely capture real-world complexities such as overlapping pills, varied lighting, and occlusions. MEDISEG addresses this gap by providing instance segmentation annotations for 32 distinct pill types across 8262 images, encompassing diverse conditions from individual pill images to cluttered dosette boxes. We trained YOLOv8 and YOLOv9 on MEDISEG to demonstrate their usability, achieving mean average precision at IoU 0.5 of 99.5 percent on the 3-Pills subset and 80.1 percent on the 32-Pills subset. We further evaluate MEDISEG under a few-shot detection protocol, demonstrating that base training on MEDISEG significantly improves recognition of unseen pill classes in occluded multi-pill scenarios compared to existing datasets. These results highlight the dataset's ability not only to support robust supervised training but also to promote transferable representations under limited supervision, making it a valuable resource for developing and benchmarking AI-driven systems for medication safety.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。